A1013
Title: Censored quantile regression with time-dependent covariates
Authors: Chi Wing Chu - City University of Hong Kong (Hong Kong) [presenting]
Tony Sit - The Chinese University of Hong Kong (Hong Kong)
Zhiliang Ying - Columbia University (United States)
Abstract: A class of censored quantile regression models is proposed for right-censored failure time data with time-dependent covariates. Upon a quantile-based transformation, a system of martingale-type functional estimating equations for the quantile parameters is derived. While time-dependent covariates naturally arise in time to event analysis, the little existing literature requires either an independent censoring mechanism or a fully observed covariate process even after the event has occurred. The proposed formulation extends the existing censored quantile regression model so that only the covariate history up to the observed event time is required. A recursive algorithm is developed to evaluate the estimator numerically. Asymptotic properties including uniform consistency and weak convergence of the proposed estimator as a process of the quantile level are established. Monte Carlo simulations and numerical studies on the clinical trial data of the AIDS Clinical Trials Group are presented to illustrate the numerical performance of the proposed estimator.
